R Graphics
D-Lab and UC Berkeley Library
2017-10-27
Plotting in R
There are two major* sets of tools for creating plots in R:
Base graphics, which come with all R installations as is
ggplot2, a popular visualization package that we’ll be focusing on
*lattice is another but base and gpplot2 are by far most used
Gapminder Dataset
Gapminder is a country-year dataset with information on life expectancy, population, and GDP per capita.
dat <- read.csv("data/gapminder-FiveYearData.csv", stringsAsFactors = F)
head(dat)
## country year pop continent lifeExp gdpPercap
## 1 Afghanistan 1952 8425333 Asia 28.801 779.4453
## 2 Afghanistan 1957 9240934 Asia 30.332 820.8530
## 3 Afghanistan 1962 10267083 Asia 31.997 853.1007
## 4 Afghanistan 1967 11537966 Asia 34.020 836.1971
## 5 Afghanistan 1972 13079460 Asia 36.088 739.9811
## 6 Afghanistan 1977 14880372 Asia 38.438 786.1134
R base graphics
Minimal call takes the following form
plot(x=)
R base graphics
Basic call takes the following form
plot(x=, y=)
plot(x = dat$gdpPercap, y = dat$lifeExp)
R base graphics
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p")
R base graphics
plot(x = dat$gdpPercap, y = dat$lifeExp, type="l")
R base graphics
- “b” – both line and point plots
plot(x = dat$gdpPercap, y = dat$lifeExp, type="b")
R base graphics
- Certain plot types require different calls outside of the “type” argument
R base graphics
- breaks changes the binwidth
hist(x=dat$lifeExp, breaks=5)
R base graphics
- breaks changes the width of binwidth
hist(x=dat$lifeExp, breaks=10)
R base graphics
age.density<-density(x=dat$lifeExp, na.rm=T)
plot(x=age.density)
R base graphics
# Plot the density object, bandwidth of 0.5
plot(x=density(x=dat$lifeExp, bw=.5, na.rm=T))
R base graphics
# Plot the density object, bandwidth of 0.5
plot(x=density(x=dat$lifeExp, bw=4, na.rm=T))
R base graphics
Your turn
- Make a histogram to examine the distribution of the gdpPercap variable.
R base graphics
plot(x=, y=, type="", xlab="", ylab="", main="")
R base graphics
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p",
xlab="GDP per cap", ylab="Life Expectancy", main="Life Expectancy ~ GDP") # Add labels for axes and overall plot
R base graphics
plot(x=, y=, type="", xlim=, ylim=, cex=)
R base graphics
plot(x = dat$gdpPercap, y = dat$lifeExp)
R base graphics
plot(x = dat$gdpPercap, y = dat$lifeExp, xlim = c(1000,20000))
R base graphics
plot(x = dat$gdpPercap, y = dat$lifeExp, xlim = c(1000,20000), cex=2)
R base graphics
plot(x = dat$gdpPercap, y = dat$lifeExp, xlim = c(1000,20000), cex=0.5)
R base graphics
- Basic call with popular scaling arguments
plot(x=, y=, type="", col="", pch=, lty=, lwd=)
R base graphics
colors() # View all elements of the color vector
## [1] "white" "aliceblue" "antiquewhite"
## [4] "antiquewhite1" "antiquewhite2" "antiquewhite3"
## [7] "antiquewhite4" "aquamarine" "aquamarine1"
## [10] "aquamarine2" "aquamarine3" "aquamarine4"
## [13] "azure" "azure1" "azure2"
## [16] "azure3" "azure4" "beige"
## [19] "bisque" "bisque1" "bisque2"
## [22] "bisque3" "bisque4" "black"
## [25] "blanchedalmond" "blue" "blue1"
## [28] "blue2" "blue3" "blue4"
## [31] "blueviolet" "brown" "brown1"
## [34] "brown2" "brown3" "brown4"
## [37] "burlywood" "burlywood1" "burlywood2"
## [40] "burlywood3" "burlywood4" "cadetblue"
## [43] "cadetblue1" "cadetblue2" "cadetblue3"
## [46] "cadetblue4" "chartreuse" "chartreuse1"
## [49] "chartreuse2" "chartreuse3" "chartreuse4"
## [52] "chocolate" "chocolate1" "chocolate2"
## [55] "chocolate3" "chocolate4" "coral"
## [58] "coral1" "coral2" "coral3"
## [61] "coral4" "cornflowerblue" "cornsilk"
## [64] "cornsilk1" "cornsilk2" "cornsilk3"
## [67] "cornsilk4" "cyan" "cyan1"
## [70] "cyan2" "cyan3" "cyan4"
## [73] "darkblue" "darkcyan" "darkgoldenrod"
## [76] "darkgoldenrod1" "darkgoldenrod2" "darkgoldenrod3"
## [79] "darkgoldenrod4" "darkgray" "darkgreen"
## [82] "darkgrey" "darkkhaki" "darkmagenta"
## [85] "darkolivegreen" "darkolivegreen1" "darkolivegreen2"
## [88] "darkolivegreen3" "darkolivegreen4" "darkorange"
## [91] "darkorange1" "darkorange2" "darkorange3"
## [94] "darkorange4" "darkorchid" "darkorchid1"
## [97] "darkorchid2" "darkorchid3" "darkorchid4"
## [100] "darkred" "darksalmon" "darkseagreen"
## [103] "darkseagreen1" "darkseagreen2" "darkseagreen3"
## [106] "darkseagreen4" "darkslateblue" "darkslategray"
## [109] "darkslategray1" "darkslategray2" "darkslategray3"
## [112] "darkslategray4" "darkslategrey" "darkturquoise"
## [115] "darkviolet" "deeppink" "deeppink1"
## [118] "deeppink2" "deeppink3" "deeppink4"
## [121] "deepskyblue" "deepskyblue1" "deepskyblue2"
## [124] "deepskyblue3" "deepskyblue4" "dimgray"
## [127] "dimgrey" "dodgerblue" "dodgerblue1"
## [130] "dodgerblue2" "dodgerblue3" "dodgerblue4"
## [133] "firebrick" "firebrick1" "firebrick2"
## [136] "firebrick3" "firebrick4" "floralwhite"
## [139] "forestgreen" "gainsboro" "ghostwhite"
## [142] "gold" "gold1" "gold2"
## [145] "gold3" "gold4" "goldenrod"
## [148] "goldenrod1" "goldenrod2" "goldenrod3"
## [151] "goldenrod4" "gray" "gray0"
## [154] "gray1" "gray2" "gray3"
## [157] "gray4" "gray5" "gray6"
## [160] "gray7" "gray8" "gray9"
## [163] "gray10" "gray11" "gray12"
## [166] "gray13" "gray14" "gray15"
## [169] "gray16" "gray17" "gray18"
## [172] "gray19" "gray20" "gray21"
## [175] "gray22" "gray23" "gray24"
## [178] "gray25" "gray26" "gray27"
## [181] "gray28" "gray29" "gray30"
## [184] "gray31" "gray32" "gray33"
## [187] "gray34" "gray35" "gray36"
## [190] "gray37" "gray38" "gray39"
## [193] "gray40" "gray41" "gray42"
## [196] "gray43" "gray44" "gray45"
## [199] "gray46" "gray47" "gray48"
## [202] "gray49" "gray50" "gray51"
## [205] "gray52" "gray53" "gray54"
## [208] "gray55" "gray56" "gray57"
## [211] "gray58" "gray59" "gray60"
## [214] "gray61" "gray62" "gray63"
## [217] "gray64" "gray65" "gray66"
## [220] "gray67" "gray68" "gray69"
## [223] "gray70" "gray71" "gray72"
## [226] "gray73" "gray74" "gray75"
## [229] "gray76" "gray77" "gray78"
## [232] "gray79" "gray80" "gray81"
## [235] "gray82" "gray83" "gray84"
## [238] "gray85" "gray86" "gray87"
## [241] "gray88" "gray89" "gray90"
## [244] "gray91" "gray92" "gray93"
## [247] "gray94" "gray95" "gray96"
## [250] "gray97" "gray98" "gray99"
## [253] "gray100" "green" "green1"
## [256] "green2" "green3" "green4"
## [259] "greenyellow" "grey" "grey0"
## [262] "grey1" "grey2" "grey3"
## [265] "grey4" "grey5" "grey6"
## [268] "grey7" "grey8" "grey9"
## [271] "grey10" "grey11" "grey12"
## [274] "grey13" "grey14" "grey15"
## [277] "grey16" "grey17" "grey18"
## [280] "grey19" "grey20" "grey21"
## [283] "grey22" "grey23" "grey24"
## [286] "grey25" "grey26" "grey27"
## [289] "grey28" "grey29" "grey30"
## [292] "grey31" "grey32" "grey33"
## [295] "grey34" "grey35" "grey36"
## [298] "grey37" "grey38" "grey39"
## [301] "grey40" "grey41" "grey42"
## [304] "grey43" "grey44" "grey45"
## [307] "grey46" "grey47" "grey48"
## [310] "grey49" "grey50" "grey51"
## [313] "grey52" "grey53" "grey54"
## [316] "grey55" "grey56" "grey57"
## [319] "grey58" "grey59" "grey60"
## [322] "grey61" "grey62" "grey63"
## [325] "grey64" "grey65" "grey66"
## [328] "grey67" "grey68" "grey69"
## [331] "grey70" "grey71" "grey72"
## [334] "grey73" "grey74" "grey75"
## [337] "grey76" "grey77" "grey78"
## [340] "grey79" "grey80" "grey81"
## [343] "grey82" "grey83" "grey84"
## [346] "grey85" "grey86" "grey87"
## [349] "grey88" "grey89" "grey90"
## [352] "grey91" "grey92" "grey93"
## [355] "grey94" "grey95" "grey96"
## [358] "grey97" "grey98" "grey99"
## [361] "grey100" "honeydew" "honeydew1"
## [364] "honeydew2" "honeydew3" "honeydew4"
## [367] "hotpink" "hotpink1" "hotpink2"
## [370] "hotpink3" "hotpink4" "indianred"
## [373] "indianred1" "indianred2" "indianred3"
## [376] "indianred4" "ivory" "ivory1"
## [379] "ivory2" "ivory3" "ivory4"
## [382] "khaki" "khaki1" "khaki2"
## [385] "khaki3" "khaki4" "lavender"
## [388] "lavenderblush" "lavenderblush1" "lavenderblush2"
## [391] "lavenderblush3" "lavenderblush4" "lawngreen"
## [394] "lemonchiffon" "lemonchiffon1" "lemonchiffon2"
## [397] "lemonchiffon3" "lemonchiffon4" "lightblue"
## [400] "lightblue1" "lightblue2" "lightblue3"
## [403] "lightblue4" "lightcoral" "lightcyan"
## [406] "lightcyan1" "lightcyan2" "lightcyan3"
## [409] "lightcyan4" "lightgoldenrod" "lightgoldenrod1"
## [412] "lightgoldenrod2" "lightgoldenrod3" "lightgoldenrod4"
## [415] "lightgoldenrodyellow" "lightgray" "lightgreen"
## [418] "lightgrey" "lightpink" "lightpink1"
## [421] "lightpink2" "lightpink3" "lightpink4"
## [424] "lightsalmon" "lightsalmon1" "lightsalmon2"
## [427] "lightsalmon3" "lightsalmon4" "lightseagreen"
## [430] "lightskyblue" "lightskyblue1" "lightskyblue2"
## [433] "lightskyblue3" "lightskyblue4" "lightslateblue"
## [436] "lightslategray" "lightslategrey" "lightsteelblue"
## [439] "lightsteelblue1" "lightsteelblue2" "lightsteelblue3"
## [442] "lightsteelblue4" "lightyellow" "lightyellow1"
## [445] "lightyellow2" "lightyellow3" "lightyellow4"
## [448] "limegreen" "linen" "magenta"
## [451] "magenta1" "magenta2" "magenta3"
## [454] "magenta4" "maroon" "maroon1"
## [457] "maroon2" "maroon3" "maroon4"
## [460] "mediumaquamarine" "mediumblue" "mediumorchid"
## [463] "mediumorchid1" "mediumorchid2" "mediumorchid3"
## [466] "mediumorchid4" "mediumpurple" "mediumpurple1"
## [469] "mediumpurple2" "mediumpurple3" "mediumpurple4"
## [472] "mediumseagreen" "mediumslateblue" "mediumspringgreen"
## [475] "mediumturquoise" "mediumvioletred" "midnightblue"
## [478] "mintcream" "mistyrose" "mistyrose1"
## [481] "mistyrose2" "mistyrose3" "mistyrose4"
## [484] "moccasin" "navajowhite" "navajowhite1"
## [487] "navajowhite2" "navajowhite3" "navajowhite4"
## [490] "navy" "navyblue" "oldlace"
## [493] "olivedrab" "olivedrab1" "olivedrab2"
## [496] "olivedrab3" "olivedrab4" "orange"
## [499] "orange1" "orange2" "orange3"
## [502] "orange4" "orangered" "orangered1"
## [505] "orangered2" "orangered3" "orangered4"
## [508] "orchid" "orchid1" "orchid2"
## [511] "orchid3" "orchid4" "palegoldenrod"
## [514] "palegreen" "palegreen1" "palegreen2"
## [517] "palegreen3" "palegreen4" "paleturquoise"
## [520] "paleturquoise1" "paleturquoise2" "paleturquoise3"
## [523] "paleturquoise4" "palevioletred" "palevioletred1"
## [526] "palevioletred2" "palevioletred3" "palevioletred4"
## [529] "papayawhip" "peachpuff" "peachpuff1"
## [532] "peachpuff2" "peachpuff3" "peachpuff4"
## [535] "peru" "pink" "pink1"
## [538] "pink2" "pink3" "pink4"
## [541] "plum" "plum1" "plum2"
## [544] "plum3" "plum4" "powderblue"
## [547] "purple" "purple1" "purple2"
## [550] "purple3" "purple4" "red"
## [553] "red1" "red2" "red3"
## [556] "red4" "rosybrown" "rosybrown1"
## [559] "rosybrown2" "rosybrown3" "rosybrown4"
## [562] "royalblue" "royalblue1" "royalblue2"
## [565] "royalblue3" "royalblue4" "saddlebrown"
## [568] "salmon" "salmon1" "salmon2"
## [571] "salmon3" "salmon4" "sandybrown"
## [574] "seagreen" "seagreen1" "seagreen2"
## [577] "seagreen3" "seagreen4" "seashell"
## [580] "seashell1" "seashell2" "seashell3"
## [583] "seashell4" "sienna" "sienna1"
## [586] "sienna2" "sienna3" "sienna4"
## [589] "skyblue" "skyblue1" "skyblue2"
## [592] "skyblue3" "skyblue4" "slateblue"
## [595] "slateblue1" "slateblue2" "slateblue3"
## [598] "slateblue4" "slategray" "slategray1"
## [601] "slategray2" "slategray3" "slategray4"
## [604] "slategrey" "snow" "snow1"
## [607] "snow2" "snow3" "snow4"
## [610] "springgreen" "springgreen1" "springgreen2"
## [613] "springgreen3" "springgreen4" "steelblue"
## [616] "steelblue1" "steelblue2" "steelblue3"
## [619] "steelblue4" "tan" "tan1"
## [622] "tan2" "tan3" "tan4"
## [625] "thistle" "thistle1" "thistle2"
## [628] "thistle3" "thistle4" "tomato"
## [631] "tomato1" "tomato2" "tomato3"
## [634] "tomato4" "turquoise" "turquoise1"
## [637] "turquoise2" "turquoise3" "turquoise4"
## [640] "violet" "violetred" "violetred1"
## [643] "violetred2" "violetred3" "violetred4"
## [646] "wheat" "wheat1" "wheat2"
## [649] "wheat3" "wheat4" "whitesmoke"
## [652] "yellow" "yellow1" "yellow2"
## [655] "yellow3" "yellow4" "yellowgreen"
R base graphics
colors()[179] # View specific element of the color vector
## [1] "gray26"
R base graphics
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p", col=colors()[145]) # or col="gold3"
R base graphics
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p", col="seagreen4") # or col=colors()[578]
R base graphics
A Good Reference
# Change point style to crosses
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p", pch=3)
R base graphics
# Change point style to filled squares
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p",pch=15)
R base graphics
# Change point style to filled squares and increase point size to 3
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p",pch=15, cex=3)
R base graphics
# Change point style to "w"
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p", pch="w")
R base graphics
# Line plot with solid line
plot(x = dat$gdpPercap, y = dat$lifeExp, type="l", lty=1)
R base graphics
# Line plot with medium dashed line
plot(x = dat$gdpPercap, y = dat$lifeExp, type="l", lty=2)
R base graphics
# Change line width to 2
plot(x = dat$gdpPercap, y = dat$lifeExp, type="l", lty=3, lwd=2)
R base graphics
# Change line width to 10 and use dash-dot
plot(x = dat$gdpPercap, y = dat$lifeExp, type="l", lty=4, lwd=10)
R base graphics
- Annotations, reference lines, and legends
# plot the line first
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p")
# now add the label
text(x=40000, y=50, labels="Evens Out", cex = .75)
R base graphics
- Annotations, reference lines, and legends
# plot the line
plot(x = dat$gdpPercap, y = dat$lifeExp, type="p")
# now the guides
abline(v=40000, h=75, lty=2)
R base graphics
Your turn
Make a scatterplot with population on the x axis and life expectancy on the y axis. Change the color to “peachpuff3” and the point character to “+”
plot(x=, y=, type=, col=, pch=)
ggplot2
More elegant and compact code
Aesthetically pleasing defaults
Powerful for exploratory data analysis
Follows a grammar like a language
ggplot2
ggplot(data=, aes(x=, y=), color=, size=,) + geom_xxxx()+geom_yyyy()
The grammar involves some basic components:
- Data: a data.frame
- Aesthetics: How your data are represented visually, aka “mapping”. Which variables are shown on x, y axes, as well as color, size, shape, etc.
- Geometry: The geometric objects in a plot. points, lines, polygons, etc.
ggplot2
library(ggplot2)
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp)) + geom_point()
ggplot2
By itself, the call to ggplot isn’t enough to draw a figure:
library(ggplot2)
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp))
ggplot2
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp)) + geom_point()
equivalent to:
my_plot <- ggplot(data = dat, aes(x = gdpPercap, y = lifeExp))
my_plot + geom_point()
ggplot2
Your Turn
Modify the example so that the figure visualises how life expectancy has changed over time:
Hint: the gapminder dataset has a column called “year”, which should appear on the x-axis.
ggplot(data = , aes(x = , y = )) + geom_point()
ggplot2
Anatomy of aes
We’ve used the aes function to tell the scatterplot geom about the x and y locations of each point. Another aes property we can modify is the point color
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp, color=continent)) + geom_point()
ggplot2
Anatomy of aes
Color isn’t the only aesthetic argument we can set to display variation in the data. We can also vary by shape, size, etc.
ggplot(data=, aes(x=, y=, by =, color=, linetype=, shape=, size=))
ggplot2
Anatomy of aes
ggplot(data = dat, aes(x=year, y=lifeExp, by=country, color=continent)) + geom_line()
ggplot2
Anatomy of aes
ggplot(data = dat, aes(x=year, y=lifeExp, by=country, color=continent)) + geom_line() + geom_point()
ggplot2
Anatomy of aes
ggplot(data = dat, aes(x=year, y=lifeExp, by=country)) +
geom_line(aes(color=continent)) + geom_point()
ggplot2
Your Turn
Switch the order of the point and line layers from the previous example. What happened?
ggplot2
Labels are their own layers in ggplot.
# add x and y axis labels
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp, color=continent)) +
geom_point() + xlab("GDP per capita") + ylab("Life Expectancy") + ggtitle("My fancy graph")
ggplot2
…so are scales
# limit x axis from 1,000 to 20,000
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp, color=continent)) +
geom_point() + xlab("GDP per capita") + ylab("Life Expectancy") + ggtitle("My fancy graph") + xlim(1000, 20000)
ggplot2
Transformations and Stats
ggplot also makes it easy to overlay statistical models over the data. To demonstrate we’ll go back to an earlier example:
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp, color=continent)) + geom_point()
ggplot2
Transformations and Stats
We can change the scale of units on the x axis using the scale functions. These control the mapping between the data values and visual values of an aesthetic.
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp, color=continent)) + geom_point() + scale_x_log10()
ggplot2
Transformations and Stats
We can fit a simple relationship to the data by adding another layer, geom_smooth:
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp, color=continent)) + geom_point() + scale_x_log10() + geom_smooth(method="lm")
ggplot2
Transformations and Stats
Note that we 5 lines, one for each region, because the color option is the global aes function.. But if we move it, we get different restuls:
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp)) + geom_point(aes(color=continent)) + scale_x_log10() + geom_smooth(method="lm")
ggplot2
Transformations and Stats
ggplot(data = dat, aes(x = gdpPercap, y = lifeExp)) + geom_point(aes(color=continent)) + scale_x_log10() + geom_smooth(method="lm", size = 1.5)
ggplot2
Your Turn
Modify the color and size of the points on the point layer in the previous example so that they are fixed (i.e. not reflective of continent).
Hint: do not use the aes function.
ggplot2
Facets
ggplot(data = dat, aes(x = year, y = lifeExp)) + geom_point() + facet_wrap( ~ continent)
ggplot2
Bar Plots
ggplot(data = dat, aes(x = lifeExp)) + geom_bar(stat="bin")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ggplot2
Bar Plots
ggplot(data = dat, aes(x = lifeExp, fill = continent)) + geom_bar(stat="bin")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ggplot2
Density Plots
ggplot(dat, aes(lifeExp)) + geom_density(bw = .5, na.rm= T)
ggplot2
Box Plots
ggplot(data = dat, aes(x = continent, y = lifeExp)) + geom_boxplot()
ggplot2
Your Turn
Create a density plot of GDP per capita, filled by continent.
Transform the x axis to better visualise the data spread.
Add a facet layer to panel the density plots by year.
ggplot2
Exporting- raster/bitmap
jpeg(filename="example.png", width=, height=)
plot(x,y)
dev.off()
Exporting- Vector
pdf(filename="example.pdf", width=, height=)
plot(x,y)
dev.off()
ggplot2
Exporting with ggplot
# Assume we saved our plot is an object called example.plot
ggsave(filename="example.pdf", plot=example.plot, scale=, width=, height=)
